On the Generalized Degrees of Freedom of Noncoherent Interference Channel

TL;DR

This paper investigates the generalized degrees of freedom of the noncoherent 2-user interference channel, showing that alternative schemes like rate-splitting, TIN, and TDM outperform traditional training-based methods in various regimes.

Contribution

It introduces new noncoherent schemes, including a rate-splitting approach, and analyzes their performance, demonstrating their superiority over standard training-based schemes in different interference regimes.

Findings

Training-based scheme is suboptimal in several regimes.

TIN scheme is optimal in very weak interference.

TDM and rate-splitting schemes outperform in strong interference.

Abstract

We study the generalized degrees of freedom (gDoF) of the block-fading noncoherent 2-user interference channel (IC) with a coherence time of T symbol durations and symmetric fading statistics. We demonstrate that a natural training-based scheme for the noncoherent IC, is suboptimal in several regimes. We study and analyze several alternate schemes: the first is a new noncoherent scheme using rate-splitting. We also consider a scheme that treats interference-as-noise (TIN) and a time division multiplexing (TDM) scheme. We show that a standard training-based scheme for the noncoherent IC is outperformed by one of these schemes in several regimes: our results demonstrate that in the very weak interference regime, the TIN scheme is the best; in the strong interference regime, the TDM scheme and the noncoherent rate-splitting scheme give better performance; in other cases either of the TIN, TDM or noncoherent rate-splitting scheme could be preferred. We also study the noncoherent IC with feedback and propose another noncoherent rate-splitting scheme. Again for the feedback case, our results demonstrate that a natural training-based scheme can be outperformed by other schemes.